Post
1915
We propose MGDebugger, a hierarchical bottom-up LLM code debugger 🔥 that can fix bugs from low-level syntax errors to high-level algorithmic flaws.
It achieves an ⭐️ 18.9% improvement in accuracy over seed generations in HumanEval and a ⭐️ 97.6% repair success rate in HumanEvalFix.
Paper available at https://arxiv.org/abs/2410.01215.
Code and demo available at https://github.com/YerbaPage/MGDebugger.
It achieves an ⭐️ 18.9% improvement in accuracy over seed generations in HumanEval and a ⭐️ 97.6% repair success rate in HumanEvalFix.
Paper available at https://arxiv.org/abs/2410.01215.
Code and demo available at https://github.com/YerbaPage/MGDebugger.
